WO2022208799A1

WO2022208799A1 - Water quality management device, water quality management method, and water quality management program

Info

Publication number: WO2022208799A1
Application number: PCT/JP2021/014000
Authority: WO
Inventors: 敏治柳川; 圭二尾山; 一憲小路; 義文旭; 一朗勝山; 有頂定道; 勇也鈴木; 好貴市川
Original assignee: 中国電力株式会社; 日機装株式会社; 日本エヌ・ユー・エス株式会社
Priority date: 2021-03-31
Filing date: 2021-03-31
Publication date: 2022-10-06
Also published as: JPWO2022208799A1; JP7101912B1; TW202242728A

Abstract

Provided are a water quality management device, a water quality management method, and a water quality management program with which it is possible to prevent the residual chlorine concentration in seawater from exceeding a reference value at a seawater discharge port. This water quality management device for use in a seawater utilization plant comprises: an attribute value acquisition unit that acquires an attribute value pertaining to seawater flowing through a condenser installed in the seawater utilization plant; a concentration prediction unit that, on the basis of the attribute value, predicts the residual chlorine concentration at a discharge port of a discharge path through which seawater is discharged from the condenser to the sea; a required amount calculation unit that, on the basis of the predicted residual chlorine concentration, calculates the required amount of a residual chlorine neutralizer to be injected into the discharge path; and a neutralizer injection unit that injects the neutralizer into the discharge path in the required amount.

Description

Water quality control device, water quality control method, and water quality control program

The present invention relates to a water quality control device, a water quality control method, and a water quality control program. More specifically, the present invention relates to a water quality control device, a water quality control method, and a water quality control program used in a seawater utilization plant such as a power plant.

Seawater electrolytic chlorine (sodium hypochlorite) is generated as a countermeasure against adherent organisms such as barnacles and mussels, and biofilms that adhere to the seawater system of seawater plants such as thermal power plants and nuclear power plants. Therefore, the technique of injecting water into the water intake is widely practiced.

For example, in Patent Document 1, sodium hypochlorite is generated by electrolyzing natural seawater, and an electrolytic solution containing the sodium hypochlorite is injected into a seawater intake to prevent adhesion of marine organisms. technology used for

Japanese Patent No. 4932529

When injecting seawater electrochlorine into the water intake, it is necessary to inject it so that the residual chlorine concentration at the seawater discharge port does not exceed the standard value. Since the attenuation rate differs depending on the water quality and water quality, there is a risk that the standard value will be temporarily exceeded at the water discharge port if an attempt is made to maintain the residual chlorine concentration that is effective in preventing fouling organisms. Therefore, there is a demand for a technology that prevents the concentration of residual chlorine from exceeding the reference value by injecting an appropriate amount of neutralizing agent at an appropriate timing.

The present invention has been made in view of the above problems, and is capable of preventing the concentration of residual chlorine in seawater from exceeding a reference value in a seawater outlet, a water quality control device, a water quality control method, and Intended to provide a water quality management program.

The present invention provides a water quality control device for a seawater utilization plant, comprising: an attribute value acquisition unit for acquiring an attribute value of seawater flowing through a condenser installed in the seawater utilization plant; a concentration prediction unit that predicts the residual chlorine concentration at the outlet of the discharge channel that discharges the seawater from the condenser to the sea; and a residual chlorine injected into the discharge channel based on the predicted residual chlorine concentration The present invention relates to a water quality control device comprising a required amount calculation unit that calculates a required amount of a chlorine neutralizer, and a neutralizer injection unit that injects the required amount of the neutralizer into the discharge channel.

In addition, the attribute value includes the concentration of residual chlorine in seawater at the intake of the condenser, the water temperature of seawater at the outlet of the condenser, the flow time of seawater from the intake to the discharge, and the concentration It is preferable that the prediction unit predicts the residual chlorine concentration at the water outlet by applying the attribute value to the Arrhenius equation.

Further, in the water quality control device, the concentration prediction unit inputs history data of attribute values including residual chlorine concentration, salinity, pH, ORP (oxidation-reduction potential), and water temperature of seawater at the inlet of the condenser. a label acquisition unit that acquires history data of the residual chlorine concentration in the water discharge port as a label; and a set of the input data and the label as learning data, the residual chlorine in the water discharge port A learning unit that builds a learning model for estimating the concentration, and an estimated value generating unit that generates an estimated value of the residual chlorine concentration by applying a new attribute value to the learning model after building the learning model. It is preferable to have

Also, in the water quality control device, the learning unit preferably constructs the learning model using a random forest.

Further, in the water quality control device, the learning unit preferably constructs the learning model using generalized addition (GAM method).

The present invention also provides a water quality management method for a seawater utilization plant, comprising: an attribute value acquisition step of acquiring an attribute value of seawater flowing through a condenser installed in the seawater utilization plant; a concentration prediction step of predicting a residual chlorine concentration at an outlet of a discharge channel that discharges the seawater from the condenser to the sea, based on the predicted residual chlorine concentration; The present invention relates to a water quality control method comprising a required amount calculation step of calculating a required amount of a neutralizer for residual chlorine, and a neutralizer injection step of injecting the required amount of the neutralizer into the discharge channel.

The present invention also provides a water quality management program for a seawater utilization plant, comprising: an attribute value obtaining step of obtaining an attribute value of seawater flowing through a condenser installed in the seawater utilization plant; a concentration prediction step of predicting a residual chlorine concentration at an outlet of a discharge channel that discharges the seawater from the condenser to the sea, based on the predicted residual chlorine concentration; Water quality management for causing a computer to execute a required amount calculation step of calculating a required amount of a neutralizer for residual chlorine and a neutralizer injection step of injecting the required amount of the neutralizer into the discharge channel. Regarding the program.

According to the present invention, it is possible to prevent the concentration of residual chlorine in seawater from exceeding the standard value at the seawater outlet.

1 is an overall configuration diagram of a seawater utilization plant according to an embodiment of the present invention; FIG. 1 is a functional block diagram of a water quality control device according to an embodiment of the present invention; FIG. It is a flowchart which shows operation|movement of the water-quality control apparatus which concerns on embodiment of this invention. It is a functional block diagram of a concentration prediction part included in the water quality control device according to the embodiment of the present invention. It is a flowchart which shows operation|movement of the water-quality control apparatus which concerns on embodiment of this invention. It is a flowchart which shows operation|movement of the water-quality control apparatus which concerns on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. It is a figure which shows the Arrhenius equation based on embodiment of this invention. FIG. 5 is a diagram showing a comparison between original data and prediction results by random forest according to the embodiment of the present invention; FIG. 5 is a diagram showing a comparison between original data and prediction results by random forest according to the embodiment of the present invention; It is a figure which shows the comparison of the original data and the prediction result by generalized addition method (GAM) based on embodiment of this invention. It is a figure which shows the comparison of the original data and the prediction result by generalized addition method (GAM) based on embodiment of this invention. It is a figure which shows the comparison of the original data and the prediction result by generalized addition method (GAM) based on embodiment of this invention. It is a figure which shows the comparison of the original data and the prediction result by generalized addition method (GAM) based on embodiment of this invention. It is a figure which shows the comparison of the original data and the prediction result by generalized addition method (GAM) based on embodiment of this invention. It is a figure which shows the comparison of the original data and the prediction result by generalized addition method (GAM) based on embodiment of this invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[1 Outline of the invention]
FIG. 1 is an overall configuration diagram of a seawater utilization plant 100 including a water quality control device 1 and a condenser 2 according to this embodiment. In the seawater utilization plant 100, the condenser 2 takes in seawater as cooling water from the sea 3A through the water intake channel 21, and after cooling the steam turbine and the like, the cooling water is discharged from the outlet 221 of the condenser 2. The water is discharged to the sea 3B through the waterway 22. At the chlorine injection point of the intake channel 21, a seawater electrolytic solution containing sodium hypochlorite is injected.

The water quality control device 1 predicts the residual chlorine concentration at the water outlet 222 of the water discharge channel 22 based on the attribute values of the seawater flowing through the condenser 2, and compares it with the residual chlorine concentration of the seawater at the condenser inlet 211. After calculating the amount of decrease, the required amount of the neutralizer is calculated based on the amount of decrease, and the required amount of the neutralizer is injected into the discharge channel 22 .

[2 First embodiment]
A water quality control device 1 according to a first embodiment of the present invention will be described below with reference to FIGS. 2 and 3. FIG.

[2.1 Configuration of Embodiment]
FIG. 2 is a functional block diagram of the water quality control device 1. As shown in FIG. The water quality control device 1 includes a control section 11 , a neutralizing agent injection section 12 and a storage section 13 .

The control unit 11 is a part that controls the entire water quality management apparatus 1, and by reading and executing various programs from a storage area such as a ROM, a RAM, a flash memory, or a hard disk (HDD), the Various functions are realized. The control unit 11 may be a CPU. The control unit 11 includes an attribute value acquisition unit 111 , a concentration prediction unit 112 and a required amount calculation unit 113 .

In addition, the control unit 11 includes general functional blocks such as a functional block for controlling the entire water quality management device 1 and a functional block for communication. However, since these general functional blocks are well known to those skilled in the art, illustration and description are omitted.

The attribute value acquisition unit 111 acquires attribute values of seawater flowing through the condenser 2 . More specifically, for example, a pumping pump (not shown) installed outside the water quality control device 1 pumps up seawater from the water intake channel 21, and the pumped seawater is treated with the water quality installed outside the water quality control device 1. Analyze with an analyzer (not shown). The attribute value acquisition unit 111 acquires attribute values related to the water quality of seawater analyzed by the water quality analyzer. Furthermore, the attribute value acquisition unit 111 acquires the water temperature of seawater at the outlet 221 of the condenser 2, the flow time of seawater from the condenser inlet 211 to the water outlet 222, and the like as attribute values.

Here, as attribute values related to water quality, for example, in addition to the residual chlorine concentration and water temperature of the seawater at the condenser inlet 211, for the purpose of improving accuracy, the concentration of organic matter, the amount of salt contained in the seawater, pH, ORP (oxidation-reduction potential).

The concentration prediction unit 112 predicts the residual chlorine concentration at the seawater water outlet 222 based on the attribute value acquired by the attribute value acquisition unit 111 . In particular, in this embodiment, the concentration prediction unit 112 uses, as attribute values, the residual chlorine concentration of seawater at the inlet 211 of the condenser 2, the water temperature of the seawater at the outlet 221 of the condenser 2, the inlet 211 of the condenser 2 The residual chlorine concentration at the seawater outlet 222 is estimated by applying the Arrheinius equation to the flow time of seawater from the outlet 222 to the outlet 222 .

Here, the “Arrheinius equation” is an equation that predicts the rate of a chemical reaction at a certain temperature, and the reaction constant k that indicates the reaction rate is the temperature T is high and the activation energy E _a is low.

Here, _A is a constant (frequency factor) independent of temperature, Ea is the activation energy per 1 mol, R is the gas constant, and T is the absolute temperature. Here, the "frequency factor" is a factor representing the number of collisions between molecules in a bimolecular reaction.

Based on the residual chlorine concentration predicted by the concentration prediction unit 112, the required amount calculation unit 113 calculates the necessary amount of the residual chlorine neutralizer to be injected into the water discharge channel 22. More specifically, the required amount calculation unit 113 calculates the required amount of the neutralizer based on the amount of decrease in the estimated residual chlorine concentration at the water outlet 222 compared to the residual chlorine concentration at the water intake 211 .

Here, the neutralizing agent may be an existing agent capable of rapidly neutralizing residual chlorine, such as 35% hydrogen peroxide, sodium sulfite, or sodium thiosulfate. When 35% hydrogen peroxide solution is used, reaction by-products are oxygen, water, and chloride ions, and when sodium sulfite is used, reaction by-products are sulfate ions and chloride ions. Both of these are abundant in seawater.

The neutralizer injection unit 12 injects the necessary amount of neutralizer calculated by the necessary amount calculation unit 113 into the water discharge channel 22 . In particular, it is preferable to automatically control the injection of the neutralizer into the discharge channel 22 by the neutralizer injector 12 .

The storage unit 13 stores the attribute value acquired by the attribute value acquisition unit 111, the residual chlorine concentration predicted by the concentration prediction unit 112, and the required amount of neutralizer calculated by the required amount calculation unit 113.

[2.2 Operation of Embodiment]
FIG. 3 is a flow chart showing the operation of the water quality control device 1. As shown in FIG.

In step S1, the attribute value acquisition unit 111 acquires the attribute value of the water quality at the seawater intake 211, the water temperature of the seawater at the outlet 221 of the condenser 2, the flow time of the seawater from the inlet 211 to the water outlet 222, and the like. do.

In step S<b>2 , the concentration prediction unit 112 predicts the residual chlorine concentration at the seawater outlet 222 based on the attribute value acquired by the attribute value acquisition unit 111 .

In step S3, the required amount calculation unit 113 calculates the required amount of the residual chlorine neutralizer to be injected into the discharge channel 22 based on the residual chlorine concentration predicted by the concentration prediction unit 112.

In step S<b>4 , the neutralizer injection unit 12 injects the necessary amount of neutralizer calculated by the necessary amount calculation unit 113 into the water discharge channel 22 .

[2.3 Effects of Embodiment]
A water quality control device 1 according to the present embodiment is a water quality control device 1 for a seawater utilization plant 100, and is an attribute value for acquiring an attribute value of seawater flowing through a condenser 2 installed in the seawater utilization plant 100. An acquisition unit 111, a concentration prediction unit 112 that predicts the residual chlorine concentration at the outlet 222 of the discharge channel 22 that discharges seawater from the condenser 2 to the sea based on the attribute value, and a concentration prediction unit 112 that predicts, based on the estimated residual chlorine concentration a required amount calculation unit 113 for calculating the required amount of the neutralizing agent for residual chlorine to be injected into the discharge channel 22; Prepare.

This makes it possible to prevent the residual chlorine concentration in seawater from exceeding the standard value at the seawater outlet. Above all, by injecting an appropriate amount of the neutralizing agent before the residual chlorine concentration at the water outlet 222 exceeds the standard value, it is possible to prevent exceeding the standard value. As a result, it is possible to adjust the base value of the electrolytic chlorine injection concentration to a higher value, and by more effectively suppressing the adhesion of attached organisms and biofilms that hinder power generation, the heat exchange efficiency of the condenser 2 is improved, resulting in significant cost savings.

In the water quality control device 1, the above attribute values are the residual chlorine concentration of seawater at the inlet 211 of the condenser 2, the water temperature of the seawater at the outlet 221 of the condenser 2, and the seawater temperature from the outlet 221 to the water discharge port 222. Including the flow time, the concentration prediction unit predicts the residual chlorine concentration at the water outlet 222 by applying the above attribute value to the Arrhenius equation.

As a result, by using the Arrhenius equation, it is possible to prevent the residual chlorine concentration in seawater from exceeding the standard value.

[3 Second embodiment]
A water quality control device 1A, which is a second embodiment of the present invention, will be described below with reference to FIGS. 4 to 6. FIG. In the following, for the sake of simplification of explanation, mainly the differences between the water quality control device 1A and the water quality control device 1 will be explained.

[3.1 Configuration of Embodiment]
The basic configuration of the water quality control device 1A is the same as that of the water quality control device 1 shown in FIG. However, the water quality control device 1A includes a concentration prediction unit 112A instead of the concentration prediction unit 112 included in the water quality control device 1. FIG. The concentration prediction unit 112 mainly uses the Arrhenius equation to predict the residual chlorine concentration at the water discharge port 222, while the concentration prediction unit 112A predicts the residual chlorine concentration at the water discharge port 222 by machine learning.

FIG. 4 is a functional block diagram of the concentration prediction unit 112A. The concentration prediction unit 112A includes an input data acquisition unit 114, a label acquisition unit 115, a learning unit 116, and an estimated value generation unit 117. FIG.

The input data acquisition unit 114 acquires, from the storage unit 13, history data of attribute values including the residual chlorine concentration, salinity, pH, ORP (oxidation-reduction potential), and water temperature of the seawater in the water intake 211 as input data to be used for machine learning. to get as

The label acquisition unit 115 acquires history data of the residual chlorine concentration at the water outlet 222 from the storage unit 13 as labels used for machine learning.

The learning unit 116 constructs a learning model for estimating the residual chlorine concentration at the water outlet 222 by performing machine learning using pairs of input data and labels as learning data, and stores the constructed learning model in the storage unit 13. .

Here, when a set of input data and a label is used as learning data, considering the flow time of seawater from the outlet 221 of the condenser 2 to the water discharge port 222, It is processed so that it is paired with the water outlet data. Further, for example, negative values may be regarded as abnormal values and removed for both the objective variable and the explanatory variable.

The machine learning performed by the learning unit 116 may be random forest or generalized addition (GAM method). Here, "random forest" is one of machine learning algorithms, and a decision tree is used as a weak learner. is an algorithm that improves
In addition, "generalized addition" is an algorithm that uses a model in which the linear predictor in the generalized linear model is the sum of nonlinear functions. , B spline, natural spline, etc. are used. Among them, an algorithm using a smoothing spline as a non-linear function is called a "GAM method".

After the learning model is constructed by the learning unit 116 and the constructed learning model is stored in the storage unit 13, the estimated value generation unit 117 acquires the learning model from the storage unit 13 and generates new attribute values in the learning model. produces an estimate of the residual chlorine concentration at the outlet 222 by applying .

[3.2 Operation of Embodiment]
FIG. 5 is a flow chart showing the operation of the water quality control device 1A during machine learning.

In step S11, the input data acquisition unit 114 acquires history data of attribute values including residual chlorine concentration, salinity, pH, ORP (oxidation-reduction potential), water temperature, and flow rate of seawater from the storage unit 13 as input data. .

In step S12, the label acquisition unit 115 acquires history data of the residual chlorine concentration at the water outlet as a label.

In step S13, the learning unit 116 treats pairs of input data and labels as learning data.

In step S14, the learning unit 116 performs machine learning using the learning data.

At step S15, if the machine learning has ended (S15: YES), the process proceeds to step S16. If the machine learning has not ended (S15: NO), the process proceeds to step S11.

In step S16, the learning unit 116 stores the constructed learning model in the storage unit 13.

FIG. 6 is a flow chart showing the operation of the water quality control device 1A when injecting the neutralizer.

In step S21, the estimated value generation unit 117 acquires the learning model from the storage unit 13.

In step S22, the estimated value generation unit 117 acquires new attribute values from the attribute value acquisition unit 111.

In step S23, the estimated value generator 117 generates an estimated value (predicted value) of the residual chlorine concentration at the water outlet 222 by applying the new attribute value to the learning model.

In step S24, the required amount calculation unit 113 calculates the required amount of the residual chlorine neutralizer to be injected into the water discharge channel 22 based on the residual chlorine concentration predicted by the concentration prediction unit 112.

In step S<b>25 , the neutralizing agent injection unit 12 injects the necessary amount of neutralizing agent calculated by the necessary amount calculating unit 113 into the discharge channel 22 .

[3.3 Effects of Embodiment]
In the water quality control device 1A, the concentration prediction unit 112A acquires history data of attribute values including the residual chlorine concentration, salinity, pH, ORP (oxidation-reduction potential), and water temperature of the seawater at the water intake 211 as input data. An acquisition unit 114, a label acquisition unit 115 that acquires history data of the residual chlorine concentration in the water outlet 222 as a label, and a learning model that estimates the residual chlorine concentration in the water outlet using a set of input data and label as learning data. and an estimated value generation unit 117 that generates an estimated value of the residual chlorine concentration by applying a new attribute value to the learning model after building the learning model.

As a result, it is possible to inject the neutralizing agent into the discharge channel 22 based on a more accurate residual chlorine concentration predicted value.

Also, the learning unit 116 builds a learning model using a random forest.

This makes it possible to handle a large number of explanatory variables and perform high-speed learning, as well as calculate the importance (contribution) of the explanatory variables.

Also, the learning unit 116 constructs a learning model using generalized addition.

As a result, by using a function with a complex form, it is possible to explain things that are not simple proportional relationships, and to improve the accuracy of prediction while maintaining the explainability of the linear model.

[4 Prediction data]
[4.1 Arrhenius equation]
(1) Analysis based on data from June 29, 2018 to November 9, 2018 Measurement data from June 29, 2018 to November 9, 2018 of A Power Station Unit 1 (maximum output 340 MW) was used

(1-1) Relationship with Condenser Inlet Concentration It is also known that the initial concentration contributes greatly to the attenuation of the residual chlorine concentration. Regarding the Arrhenius formula shown in (1-1), the residual chlorine concentration at the condenser inlet is 0.05 mg / L or more, 0.03 mg / L or more and less than 0.05 mg / L, less than 0.03 mg / L for each power generation output , and the Arrhenius equations for each case are shown in FIGS. 7A to 9C.

In any case of power generation output, the higher the residual chlorine concentration, the higher the coefficient of determination. The highest coefficient of determination was 0.589 when the power generation output was 200 MW or more and the residual chlorine concentration was 0.05 mg/L or more. When the residual chlorine concentration is less than 0.03, the coefficient of determination is less than 0.05 in any case of power generation output.

[4.2 Machine learning]
We investigated the applicability of machine learning as a method to predict the residual chlorine concentration at the outlet from the residual chlorine concentration at the condenser inlet.

(1) Data used The data used for model construction and prediction was the 1-minute value from June 29, 2018 to March 31, 2019 at Unit 1 of A power plant. The variables used and data processing methods are shown in the table below.

(2) Results from Prediction Models Using the processed data, predictions were made using two prediction models, random forest and generalized additive model (GAM).

(2-1) Prediction results by random forest Data from June 29, 2018 to February 28, 2019 were used as learning data, and predictions from March 1, 2019 to March 31, 2019 were made. 10A and 10B show a comparison between original data and prediction results.

The original data and prediction results show similar behavior. Although it is generally within the range of 0.01 mg/L with respect to the original data, the coefficient of determination between the original data and the prediction result is as low as 0.096 because the distribution of errors is biased.

(2-2) Prediction Results by Generalized Additive Method (GAM) Three predictions were made by changing the learning range and the prediction range.

1) Prediction result 1
As with the prediction using random forest, the data from June 29, 2018 to February 28, 2019 was used as learning data, and the prediction from March 1, 2019 to March 31, 2019 was made. 11A and 11B show a comparison between original data and prediction results.

As with the random forest results, the original data and prediction results show similar behavior. Compared to the original data, it is generally within the range of 0.01 mg/L or less, and there is little bias in the error distribution, so the coefficient of determination between the original data and the prediction results is 0.272, which is higher than the results from the random forest. there is

2) Prediction result 2
The results shown in the previous section differed in the learning period and prediction period. Forecasts were made from November 1, 2018 to November 30, 2018. 12A and 12B show a comparison between original data and prediction results.

As with prediction result 1, the original data and the prediction result show similar behavior. It was generally within the range of 0.01 mg/L with respect to the original data, and the coefficient of determination between the original data and the prediction result was 0.303.

3) Prediction result 3
Data from February 1, 2019 to February 14, 2019 were used as learning data, and predictions were made from February 15, 2019 to February 20, 2019. 13A and 13B show a comparison between original data and prediction results.

The behavior of the original data and the prediction results are almost identical, demonstrating high reproducibility. It is generally within the range of about 0.005 mg/L with respect to the original data, and the coefficient of determination between the original data and the prediction result is as high as 0.505.

[4.3 Summary]
In the attenuation reaction from the condenser inlet to the outlet, when the power output is 200 MW or more and the residual chlorine concentration at the condenser inlet is 0.05 mg / L or more, the coefficient of determination of the approximated curve by the Arrhenius equation is the highest, It was confirmed that the lower the power output and residual chlorine concentration, the lower the coefficient of determination. From this, it is considered that the prediction of outlet concentration by the Arrhenius equation is more effective as the power generation output is higher and the concentration at the condenser inlet is higher.

　As a result of verifying the prediction of outlet concentration by machine learning using multiple models and conditions, we were able to confirm the accuracy of the prediction with practicality and demonstrated its applicability.

The management method by the water

quality management device

1 or 1A is realized by software. When realized by software, a program that constitutes this software is installed in the computer (water

quality management device

1 or 1A). These programs may be recorded on removable media and distributed to users, or may be distributed by being downloaded to users' computers via a network. Furthermore, these programs may be provided to the user's computer (water

quality control device

1 or 1A) as a web service via a network without being downloaded.

1, 1A Water quality control device 2 Condenser 11 Control unit 12 Neutralizing agent injection unit 13 Storage unit 21 Water intake channel 22 Discharge channel 111 Attribute

value acquisition unit

112, 112A Concentration prediction unit 113 Required amount calculation unit 114 Input data acquisition unit 115 Label acquisition unit 116 Learning unit 117 Estimated value generation unit

Claims

A water quality control device for a seawater utilization plant, comprising:
an attribute value acquisition unit that acquires an attribute value of seawater flowing through a condenser installed in the seawater utilization plant;
a concentration prediction unit that predicts, based on the attribute value, the concentration of residual chlorine at a discharge port of a discharge channel that discharges the seawater from the condenser to the sea;
a required amount calculation unit that calculates a required amount of a neutralizing agent for residual chlorine to be injected into the discharge channel based on the predicted residual chlorine concentration;
a neutralizing agent injection unit that injects the necessary amount of the neutralizing agent into the discharge channel.
The attribute values include the residual chlorine concentration of seawater at the water intake of the condenser, the water temperature of seawater at the outlet of the condenser, and the flow time of seawater from the water intake to the water discharge,
The water quality control device according to claim 1, wherein the concentration prediction unit predicts the residual chlorine concentration at the water outlet by applying the attribute value to the Arrhenius equation.
The concentration prediction unit
an input data acquisition unit that acquires, as input data, history data of attribute values including residual chlorine concentration, salinity, pH, ORP (oxidation-reduction potential), and water temperature of seawater at the inlet of the condenser;
a label acquisition unit that acquires history data of residual chlorine concentration in the water outlet as a label;
a learning unit that constructs a learning model for estimating the residual chlorine concentration at the water outlet using the set of the input data and the label as learning data;
2. The water quality control device according to claim 1, further comprising an estimated value generation unit that generates an estimated value of the residual chlorine concentration by applying a new attribute value to the learning model after construction of the learning model.
The water quality control device according to claim 3, wherein the learning unit builds the learning model using a random forest.
The water quality control device according to claim 3, wherein the learning unit builds the learning model using generalized addition.
A water quality control method for a seawater utilization plant, comprising:
an attribute value acquisition step of acquiring an attribute value of seawater flowing through a condenser installed in the seawater utilization plant;
a concentration prediction step of predicting, based on the attribute value, a residual chlorine concentration at a discharge port of a discharge channel that discharges the seawater from the condenser to the sea;
a required amount calculating step of calculating a required amount of a neutralizing agent for residual chlorine to be injected into the discharge channel based on the predicted residual chlorine concentration;
and a neutralizing agent injection step of injecting the necessary amount of the neutralizing agent into the discharge channel.
A water quality control program for a seawater plant, comprising:
an attribute value acquisition step of acquiring an attribute value of seawater flowing through a condenser installed in the seawater utilization plant;
a concentration prediction step of predicting, based on the attribute value, a residual chlorine concentration at a discharge port of a discharge channel that discharges the seawater from the condenser to the sea;
a required amount calculating step of calculating a required amount of a neutralizing agent for residual chlorine to be injected into the discharge channel based on the predicted residual chlorine concentration;
a neutralizing agent injection step of injecting the necessary amount of the neutralizing agent into the discharge channel;
A water quality management program that allows a computer to execute